ppo-Huggy / run_logs /timers.json
rakib730's picture
Huggy
f80941c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052964448928833,
"min": 1.4052742719650269,
"max": 1.4307782649993896,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71431.21875,
"min": 68957.8125,
"max": 75332.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.3879173290938,
"min": 73.26894502228826,
"max": 359.27338129496405,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48677.0,
"min": 48677.0,
"max": 50052.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49976.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49976.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5098538398742676,
"min": 0.10373128205537796,
"max": 2.5333800315856934,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1578.6981201171875,
"min": 14.314916610717773,
"max": 1659.34423828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8944909187871817,
"min": 1.6450849885957828,
"max": 4.029685416556241,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2449.634787917137,
"min": 227.02172842621803,
"max": 2591.6488012075424,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8944909187871817,
"min": 1.6450849885957828,
"max": 4.029685416556241,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2449.634787917137,
"min": 227.02172842621803,
"max": 2591.6488012075424,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018146949104751304,
"min": 0.012867009571224722,
"max": 0.01987929474853445,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054440847314253915,
"min": 0.025734019142449445,
"max": 0.05529977706610225,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05579467179874579,
"min": 0.022311599552631376,
"max": 0.06292261729637781,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16738401539623737,
"min": 0.04500044261415799,
"max": 0.18876785188913342,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6877487707833322e-06,
"min": 3.6877487707833322e-06,
"max": 0.00029535135154955,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1063246312349996e-05,
"min": 1.1063246312349996e-05,
"max": 0.0008442828185724001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122921666666668,
"min": 0.10122921666666668,
"max": 0.19845044999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30368765000000003,
"min": 0.20759135,
"max": 0.5814275999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.133791166666662e-05,
"min": 7.133791166666662e-05,
"max": 0.004922677455,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021401373499999987,
"min": 0.00021401373499999987,
"max": 0.014073237239999998,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1746086696",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746089101"
},
"total": 2404.856825215,
"count": 1,
"self": 0.444348441999864,
"children": {
"run_training.setup": {
"total": 0.023275338999837913,
"count": 1,
"self": 0.023275338999837913
},
"TrainerController.start_learning": {
"total": 2404.389201434,
"count": 1,
"self": 4.135262520977449,
"children": {
"TrainerController._reset_env": {
"total": 3.5143846339999527,
"count": 1,
"self": 3.5143846339999527
},
"TrainerController.advance": {
"total": 2396.636596434023,
"count": 233433,
"self": 4.3780918420061425,
"children": {
"env_step": {
"total": 1892.7078280329797,
"count": 233433,
"self": 1495.4576182098679,
"children": {
"SubprocessEnvManager._take_step": {
"total": 394.7803272920355,
"count": 233433,
"self": 15.100766343983423,
"children": {
"TorchPolicy.evaluate": {
"total": 379.6795609480521,
"count": 223063,
"self": 379.6795609480521
}
}
},
"workers": {
"total": 2.469882531076337,
"count": 233433,
"self": 0.0,
"children": {
"worker_root": {
"total": 2397.350184798905,
"count": 233433,
"is_parallel": true,
"self": 1172.7880158928153,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008365999999568885,
"count": 1,
"is_parallel": true,
"self": 0.00024643300002935575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005901669999275327,
"count": 2,
"is_parallel": true,
"self": 0.0005901669999275327
}
}
},
"UnityEnvironment.step": {
"total": 0.02871961400001055,
"count": 1,
"is_parallel": true,
"self": 0.00034269000002495886,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021122800012562948,
"count": 1,
"is_parallel": true,
"self": 0.00021122800012562948
},
"communicator.exchange": {
"total": 0.027509738999924593,
"count": 1,
"is_parallel": true,
"self": 0.027509738999924593
},
"steps_from_proto": {
"total": 0.0006559569999353698,
"count": 1,
"is_parallel": true,
"self": 0.000183521999815639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047243500011973083,
"count": 2,
"is_parallel": true,
"self": 0.00047243500011973083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1224.5621689060897,
"count": 233432,
"is_parallel": true,
"self": 36.70601158229806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.7371384308342,
"count": 233432,
"is_parallel": true,
"self": 78.7371384308342
},
"communicator.exchange": {
"total": 1024.243981891936,
"count": 233432,
"is_parallel": true,
"self": 1024.243981891936
},
"steps_from_proto": {
"total": 84.87503700102138,
"count": 233432,
"is_parallel": true,
"self": 29.727809249094435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.14722775192695,
"count": 466864,
"is_parallel": true,
"self": 55.14722775192695
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.55067655903736,
"count": 233433,
"self": 6.269821849031132,
"children": {
"process_trajectory": {
"total": 165.4793597090054,
"count": 233433,
"self": 164.20211259600478,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2772471130006124,
"count": 10,
"self": 1.2772471130006124
}
}
},
"_update_policy": {
"total": 327.80149500100083,
"count": 97,
"self": 262.14934029899086,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.65215470200997,
"count": 2910,
"self": 65.65215470200997
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.309998520417139e-07,
"count": 1,
"self": 8.309998520417139e-07
},
"TrainerController._save_models": {
"total": 0.1029570139999123,
"count": 1,
"self": 0.0018184919999839622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10113852199992834,
"count": 1,
"self": 0.10113852199992834
}
}
}
}
}
}
}